Methods › Natural Language Processing › Transformers › ERNIE

ERNIE

54 papers tagged archive 2025-07-28

Introduced by Yu Sun et al. in ERNIE: Enhanced Representation through Knowledge Integration

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

ERNIE is a transformer-based model consisting of two stacked modules: 1) textual encoder and 2) knowledgeable encoder, which is responsible to integrate extra token-oriented knowledge information into textual information. This layer consists of stacked aggregators, designed for encoding both tokens and entities as well as fusing their heterogeneous features. To integrate this layer of enhancing representations via knowledge, a special pre-training task is adopted for ERNIE - it involves randomly masking token-entity alignments and training the model to predict all corresponding entities based on aligned tokens (aka denoising entity auto-encoder).

PaperSource

Papers archive 2025-07-28

30 shown of 54, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 94 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling16
Language Modeling12
Named Entity Recognition (NER)5
Natural Language Inference5
Sentence5
Sentiment Analysis5
Named Entity Recognition4
Question Answering4
Benchmarking3
Classification3
GPU3
Knowledge Distillation3
Knowledge Graphs3
NER3
Semantic Textual Similarity3
Text Generation3
named-entity-recognition3
CPU2
Chinese Named Entity Recognition2
Chinese Sentence Pair Classification2

Usage over time archive 2025-07-28

Papers per year tagged with ERNIE: 2019 to 2024, peak 13 13 0 2019: 4 papers 2019 2020: 8 papers 2020 2021: 13 papers 2021 2022: 11 papers 2022 2023: 10 papers 2023 2024: 8 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (54 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Transformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections